© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13470
    Prev
    Next
    INDEX
    Explanations

    instances related to weight and gravity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.62
     للاسماء
    -0.57
    <()>
    -0.52
     كومونز
    -0.51
     Infórmanos
    -0.50
    oredCriteria
    -0.50
    RTLR
    -0.46
     endwhile
    -0.42
     jScrollPane
    -0.41
     newBuilder
    -0.41
    POSITIVE LOGITS
     weight
    3.89
    weight
    3.77
    Weight
    3.61
     Weight
    3.53
     WEIGHT
    3.27
     weights
    3.27
    WEIGHT
    3.20
     Weights
    2.95
    weights
    2.92
     weigh
    2.88
    Activations Density 0.151%

    No Known Activations